Self-learning algorithm as a tool to perform adaptive behaviour in unpredictable changing environments: a case study

Authors:
Elite Sher;Angelos Chronis;Ruairi Glynn
Affiliations:
University College London, London, UK;University College London, London, UK;University College London, London, UK
Venue:
Proceedings of the Symposium on Simulation for Architecture & Urban Design
Year:
2013

Citing 4
Cited 0

The computational beauty of nature

The computational beauty of nature
Inductive machine learning of optimal modular structures: Estimating solutions using support vector machines

Artificial Intelligence for Engineering Design, Analysis and Manufacturing
Beyond simulation: designing for uncertainty and robust solutions

SpringSim '10 Proceedings of the 2010 Spring Simulation Multiconference
Pumping vs. Iron: Adaptive Structures for Whole Life Energy Savings

IE '11 Proceedings of the 2011 Seventh International Conference on Intelligent Environments

Quantified Score

Hi-index	0.00

Visualization

Abstract

Adaptive architecture is expected to improve buildings' performance and create more efficient building systems. One of the major research areas under this scope is the adaptive behaviour of structural elements according to load distribution. In order to achieve this, current studies develop structures that adapt either by following a database of pre-calculated solutions, or by using massive computation resources for real-time calculations. This study aims to achieve an adaptive behaviour in real time, affected by load distribution, by implementing learning abilities on a case-study. This is done by applying a learning algorithm - Artificial Neural Network (ANN) on a physical prototype. The ANN was trained by an optimised database of finite solutions, which was created by a Genetic Algorithm (GA). Through this method, complex calculations are conducted 'off-line' and the component operates in a 'decision-making' mode in real-time, adapting to a versatile environment while using minimal computational resources. Results show that the case study successfully exhibit self-learning, and acquired the ability to adapt to unpredictable changing forces. This method can be applied over different structural elements (façade elements, canopies, and structural components etc.) to achieve adaptation to other parameters with an unpredictable pattern such as human behaviour or weather conditions.